Khoa D. Doan | publications

2022

ACCV Unified Learning of Multipurpose Energy Based Generative Hashing Network

Doan, Khoa D, and Reddy, Chandan K

In Sixteenth Asian Conference on Computer Vision 2022

Bib
@inproceedings{doan2022genhash, bibtex_show = {true}, abbr = {ACCV}, title = {Unified Learning of Multipurpose Energy Based Generative Hashing Network}, author = {Doan, Khoa D and Reddy, Chandan K}, booktitle = {Sixteenth Asian Conference on Computer Vision}, year = {2022}, selected = {false} }
NeurIPS Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class

Doan, Khoa D, Lao, Yingjie, and Li, Ping

In Thirty-Sixth Conference on Neural Information Processing Systems 2022

Bib
@inproceedings{doan2022marksman, bibtex_show = {true}, abbr = {NeurIPS}, title = {Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class}, author = {Doan, Khoa D and Lao, Yingjie and Li, Ping}, booktitle = {Thirty-Sixth Conference on Neural Information Processing Systems}, year = {2022}, teaser = {doan2022marksman.png}, selected = {true} }
CVPR One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching

Doan, Khoa D, Yang, Peng, and Li, Ping

In Conference on Computer Vision and Pattern Recognition 2022

Bib PDF Code Slides
@inproceedings{doan2022hswd, bibtex_show = {true}, abbr = {CVPR}, title = {One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching}, author = {Doan, Khoa D and Yang, Peng and Li, Ping}, booktitle = {Conference on Computer Vision and Pattern Recognition}, year = {2022}, slides = {doan2022hswd-slides.pdf}, code = {https://github.com/khoadoan106/single_loss_quantization}, pdf = {https://openreview.net/pdf?id=uaqweIZ-9_k}, teaser = {doan2022hswd.png}, selected = {true} }

2021

NeurIPS Backdoor Attack with Imperceptible Input and Latent Modification

Doan, Khoa D, Lao, Yingjie, and Li, Ping

In Thirty-Fifth Conference on Neural Information Processing Systems 2021

Bib PDF VIDEO Code Slides

@inproceedings{doan2021wb,
  bibtex_show = {true},
  abbr = {NeurIPS},
  title = {Backdoor Attack with Imperceptible Input and Latent Modification},
  author = {Doan, Khoa D and Lao, Yingjie and Li, Ping},
  booktitle = {Thirty-Fifth Conference on Neural Information Processing Systems},
  year = {2021},
  pdf = {https://proceedings.neurips.cc/paper/2021/file/9d99197e2ebf03fc388d09f1e94af89b-Paper.pdf},
  code = {https://github.com/khoadoan106/backdoor_attacks},
  video = {https://recorder-v3.slideslive.com/?share=51522&s=8af881c0-56e8-451e-865f-adb1e90e5471},
  slides = {doan2021wb-slides.pdf},
  teaser = {doan2021wb.png},
  selected = {true}
}

ICCV LIRA: Learnable, Imperceptible and Robust Backdoor Attacks

Doan, Khoa D, Lao, Yingjie, Zhao, Weijie, and Li, Ping

In International Conference on Computer Vision 2021

Abs Bib PDF Code Poster Slides

Recently, machine learning models have demonstrated to be vulnerable to backdoor attacks, primarily due to the lack of transparency in black-box models such as deep neural networks. A third-party model can be poisoned such that it works adequately in normal conditions but behaves maliciously on samples with specific trigger patterns. However, the trigger injection function is manually defined in most existing backdoor attack methods, e.g., placing a small patch of pixels on an image or slightly deforming the image before poisoning the model. This results in a two-stage approach with a sub-optimal attack success rate and a lack of complete stealthiness under human inspection. In this paper, we propose a novel and stealthy backdoor attack framework, LIRA, which jointly learns the optimal, stealthy trigger injection function and poisons the model. We formulate such an objective as a non-convex, constrained optimization problem. Under this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on the poisoned data. Then, we solve this challenging optimization problem with an efficient, two-stage stochastic optimization procedure. Finally, the proposed attack framework achieves 100% success rates in several benchmark datasets, including MNIST, CIFAR10, GTSRB, and T-ImageNet, while simultaneously bypassing existing backdoor defense methods and human inspection.
@inproceedings{doan2021lira, bibtex_show = {true}, abbr = {ICCV}, title = {LIRA: Learnable, Imperceptible and Robust Backdoor Attacks}, author = {Doan, Khoa D and Lao, Yingjie and Zhao, Weijie and Li, Ping}, booktitle = {International Conference on Computer Vision}, code = {https://github.com/khoadoan106/backdoor_attacks}, slides = {https://github.com/sunbelbd/invisible_backdoor_attacks/raw/master/resources/ICCV2021-LIRA-Slides.pdf}, poster = {https://github.com/sunbelbd/invisible_backdoor_attacks/raw/master/resources/ICCV2021-LIRA-Poster.pdf}, pdf = {https://openaccess.thecvf.com/content/ICCV2021/papers/Doan_LIRA_Learnable_Imperceptible_and_Robust_Backdoor_Attacks_ICCV_2021_paper.pdf}, year = {2021}, teaser = {doan2021lira.png}, selected = {true} }
SIGIR Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings

Doan, Khoa D, Manchanda, Saurav, Mahapatra, Suchismit, and Reddy, Chandan K

In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 2021

Abs Bib PDF VIDEO Code Slides

Computing graph similarity is an important task in many graph-related applications such as retrieval in graph databases or graph clustering. While numerous measures have been proposed to capture the similarity between a pair of graphs, Graph Edit Distance (GED) and Maximum Common Subgraphs (MCS) are the two widely used measures in practice. GED and MCS are domain-agnostic measures of structural similarity between the graphs and define the similarity as a function of pairwise alignment of different entities (such as nodes, edges, and subgraphs) in the two graphs. The explicit explainability offered by the pairwise alignment provides transparency and justification of the similarity score, thus, GED and MCS have important practical applications. However, their exact computations are known to be NP-hard. While recently proposed neural-network based approximations have been shown to accurately compute these similarity scores, they have limited ability in providing comprehensive explanations compared to classical combinatorial algorithms, e.g., Beam search. This paper aims at efficiently approximating these domain-agnostic similarity measures through a neural network, and simultaneously learning the alignments (i.e., explanations) similar to those of classical intractable methods. Specifically, we formulate the similarity between a pair of graphs as the minimal "transformation" cost from one graph to another in the learnable node-embedding space. We show that, if node embedding is able to capture its neighborhood context closely, our proposed similarity function closely approximates both the alignment and the similarity score of classical methods. Furthermore, we also propose an efficient differentiable computation of our proposed objective for model training. Empirically, we demonstrate that the proposed method achieves up to 50%-100% reduction in the Mean Squared Error for the graph similarity approximation task and up to 20% improvement in the retrieval evaluation metrics for the graph retrieval task. The source code is available at https://github.com/khoadoan/GraphOTSim.
@inproceedings{doan2021interpretable, bibtex_show = {true}, abbr = {SIGIR}, url = {https://doi.org/10.1145/3404835.3462960}, code = {https://github.com/khoadoan/GraphOTSim}, pdf = {doan2021interpretable.pdf}, slides = {https://github.com/khoadoan/GraphOTSim/raw/main/resources/SIGIR21-fp0937-slides.pdf}, video = {https://www.youtube.com/watch?v=IWxxsuFPsgs&t=1s}, teaser = {doan2021interpretable.png}, selected = {true}, author = {Doan, Khoa D and Manchanda, Saurav and Mahapatra, Suchismit and Reddy, Chandan K}, title = {Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings}, year = {2021}, isbn = {9781450380379}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, doi = {10.1145/3404835.3462960}, booktitle = {Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {665–674}, numpages = {10}, keywords = {similarity search, model interpretability, graph similarity, GCN}, location = {Virtual Event, Canada}, series = {SIGIR '21} }

2020

WWW Efficient Implicit Unsupervised Text Hashing Using Adversarial Autoencoder

Doan, Khoa D, and Reddy, Chandan K

In Proceedings of The Web Conference 2020

Abs Bib HTML PDF

Searching for documents with semantically similar content is a fundamental problem in the information retrieval domain with various challenges, primarily, in terms of efficiency and effectiveness. Despite the promise of modeling structured dependencies in documents, several existing text hashing methods lack an efficient mechanism to incorporate such vital information. Additionally, the desired characteristics of an ideal hash function, such as robustness to noise, low quantization error and bit balance/uncorrelation, are not effectively learned with existing methods. This is because of the requirement to either tune additional hyper-parameters or optimize these heuristically and explicitly constructed cost functions. In this paper, we propose a Denoising Adversarial Binary Autoencoder (DABA) model which presents a novel representation learning framework that captures structured representation of text documents in the learned hash function. Also, adversarial training provides an alternative direction to implicitly learn a hash function that captures all the desired characteristics of an ideal hash function. Essentially, DABA adopts a novel single-optimization adversarial training procedure that minimizes the Wasserstein distance in its primal domain to regularize the encoder’s output of either a recurrent neural network or a convolutional autoencoder. We empirically demonstrate the effectiveness of our proposed method in capturing the intrinsic semantic manifold of the related documents. The proposed method outperforms the current state-of-the-art shallow and deep unsupervised hashing methods for the document retrieval task on several prominent document collections.
@inproceedings{doan2020efficient, bibtex_show = {true}, abbr = {WWW}, url = {https://doi.org/10.1145/3366423.3380150}, html = {https://dl.acm.org/doi/abs/10.1145/3366423.3380150}, pdf = {https://people.cs.vt.edu/~reddy/papers/WWW20a.pdf}, teaser = {doan2020efficient.png}, selected = {true}, author = {Doan, Khoa D and Reddy, Chandan K}, title = {Efficient Implicit Unsupervised Text Hashing Using Adversarial Autoencoder}, year = {2020}, isbn = {9781450370233}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, doi = {10.1145/3366423.3380150}, booktitle = {Proceedings of The Web Conference}, pages = {684–694}, numpages = {11}, keywords = {autoencoder, Hashing, adversarial training, deep learning.}, location = {Taipei, Taiwan}, series = {WWW '20} }
arXiv Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space

Doan, Khoa D, Manchanda, Saurav, Wang, Fengjiao, Selvaraj, Sathiya K, Bhowmik, Avradeep, and Reddy, Chandan K

arXiv preprint arXiv:2003.11774 2020

Bib
@article{doan2020imagegen, bibtex_show = {true}, abbr = {arXiv}, title = {Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space}, author = {Doan, Khoa D and Manchanda, Saurav and Wang, Fengjiao and Selvaraj, Sathiya K and Bhowmik, Avradeep and Reddy, Chandan K}, journal = {arXiv preprint arXiv:2003.11774}, year = {2020} }
arXiv Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance

Doan, Khoa D, Manchanda, Saurav, Badirli, Sarkhan, and Reddy, Chandan K

arXiv preprint arXiv:2003.00134 2020

Bib
@article{doan2020imagehash, bibtex_show = {true}, abbr = {arXiv}, title = {Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance}, author = {Doan, Khoa D and Manchanda, Saurav and Badirli, Sarkhan and Reddy, Chandan K}, journal = {arXiv preprint arXiv:2003.00134}, year = {2020} }
arXiv Regression via implicit models and optimal transport cost minimization

Manchanda, Saurav, Doan, Khoa D, Yadav, Pranjul, and Selvaraj, Sathiya K

arXiv preprint arXiv:2003.01296 2020

Bib
@article{manchanda2020regression, bibtex_show = {true}, abbr = {arXiv}, title = {Regression via implicit models and optimal transport cost minimization}, author = {Manchanda, Saurav and Doan, Khoa D and Yadav, Pranjul and Selvaraj, Sathiya K}, journal = {arXiv preprint arXiv:2003.01296}, year = {2020} }
arXiv Gradient boosting neural networks: Grownet

Badirli, Sarkhan, Liu, Xuanqing, Xing, Zhengming, Bhowmik, Avradeep, Doan, Khoa D, and Selvaraj, Sathiya K

arXiv preprint arXiv:2002.07971 2020

Abs Bib PDF Code

A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework with specific examples presented for classification, regression, and learning to rank. A fully corrective step is incorporated to remedy the pitfall of greedy function approximation of classic gradient boosting decision tree. The proposed model rendered outperforming results against state-of-the-art boosting methods in all three tasks on multiple datasets. An ablation study is performed to shed light on the effect of each model components and model hyperparameters.
@article{badirli2020gradient, bibtex_show = {true}, abbr = {arXiv}, url = {https://arxiv.org/abs/2002.07971}, code = {https://github.com/sbadirli/GrowNet}, pdf = {https://arxiv.org/pdf/2002.07971.pdf}, teaser = {badirli2020gradient.png}, selected = {true}, title = {Gradient boosting neural networks: Grownet}, author = {Badirli, Sarkhan and Liu, Xuanqing and Xing, Zhengming and Bhowmik, Avradeep and Doan, Khoa D and Selvaraj, Sathiya K}, journal = {arXiv preprint arXiv:2002.07971}, year = {2020} }

2019

BigData Targeted display advertising: the case of preferential attachment

Manchanda, Saurav, Yadav, Pranjul, Doan, Khoa D, and Selvaraj, Sathiya K

In Proceedings of the 2019 IEEE International Conference on Big Data 2019

Bib
@inproceedings{manchanda2019targeted, bibtex_show = {true}, abbr = {BigData}, title = {Targeted display advertising: the case of preferential attachment}, author = {Manchanda, Saurav and Yadav, Pranjul and Doan, Khoa D and Selvaraj, Sathiya K}, booktitle = {Proceedings of the 2019 IEEE International Conference on Big Data}, pages = {1868--1877}, year = {2019}, organization = {IEEE} }
CIKM Adversarial Factorization Autoencoder for Look-Alike Modeling

Doan, Khoa D, Yadav, Pranjul, and Reddy, Chandan K

In Proceedings of the 28th ACM International Conference on Information and Knowledge Management 2019

Abs Bib PDF

Digital advertising is performed in multiple ways, for e.g., contextual, display-based and search-based advertising. Across these avenues, the primary goal of the advertiser is to maximize the return on investment. To realize this, the advertiser often aims to target the advertisements towards a targeted set of audience as this set has a high likelihood to respond positively towards the advertisements. One such form of tailored and personalized, targeted advertising is known as look-alike modeling, where the advertiser provides a set of seed users and expects the machine learning model to identify a new set of users such that the newly identified set is similar to the seed-set with respect to the online purchasing activity. Existing look-alike modeling techniques (i.e., similarity-based and regression-based) suffer from serious limitations due to the implicit constraints induced during modeling. In addition, the high-dimensional and sparse nature of the advertising data increases the complexity. To overcome these limitations, in this paper, we propose a novel Adversarial Factorization Autoencoder that can efficiently learn a binary mapping from sparse, high-dimensional data to a binary address space through the use of an adversarial training procedure. We demonstrate the effectiveness of our proposed approach on a dataset obtained from a real-world setting and also systematically compare the performance of our proposed approach with existing look-alike modeling baselines.
@inproceedings{doan2019adversarial, bibtex_show = {true}, abbr = {CIKM}, pdf = {https://dmkd.cs.vt.edu/papers/CIKM19.pdf}, teaser = {doan2019adversarial.png}, selected = {true}, author = {Doan, Khoa D and Yadav, Pranjul and Reddy, Chandan K}, title = {Adversarial Factorization Autoencoder for Look-Alike Modeling}, year = {2019}, isbn = {9781450369763}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3357384.3357807}, doi = {10.1145/3357384.3357807}, booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management}, pages = {2803–2812}, numpages = {10}, keywords = {deep learning, autoencoder, hashing, factorization, adversarial training, look-alike modeling}, location = {Beijing, China}, series = {CIKM '19} }
PAKDD An Attentive Spatio-Temporal Neural Model for Successive Point of Interest Recommendation.

Doan, Khoa D, Yang, Guolei, and Reddy, Chandan K

In Proceedings of the 2019 Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) 2019

2017

BigData Quest for Value in Big Earth Data

Kuo, Kwo-Sen, Oloso, Amidu O, Rilee, Mike L, Doan, Khoa D, Clune, Thomas L, and Yu, Hongfeng

In EGU General Assembly Conference Abstracts 2017

Bib
@inproceedings{kuo2017quest, bibtex_show = {true}, abbr = {BigData}, title = {Quest for Value in Big Earth Data}, author = {Kuo, Kwo-Sen and Oloso, Amidu O and Rilee, Mike L and Doan, Khoa D and Clune, Thomas L and Yu, Hongfeng}, booktitle = {EGU General Assembly Conference Abstracts}, pages = {8413}, year = {2017} }

2016

BigData Evaluating the impact of data placement to spark and SciDB with an Earth Science use case

Doan, Khoa D, Oloso, Amidu O, Kuo, Kwo-Sen, Clune, Thomas L, Yu, Hongfeng, Nelson, Brian, and Zhang, Jian

In Proceedings of the 2016 IEEE International Conference on Big Data 2016

Bib
@inproceedings{doan2016evaluating, bibtex_show = {true}, abbr = {BigData}, title = {Evaluating the impact of data placement to spark and SciDB with an Earth Science use case}, author = {Doan, Khoa D and Oloso, Amidu O and Kuo, Kwo-Sen and Clune, Thomas L and Yu, Hongfeng and Nelson, Brian and Zhang, Jian}, booktitle = {Proceedings of the 2016 IEEE International Conference on Big Data}, pages = {341--346}, year = {2016}, organization = {IEEE} }
IGARSS Implications of data placement strategy to Big Data technologies based on shared-nothing architecture for geosciences

Kuo, Kwo-Sen, Oloso, Amidu, Doan, Khoa D, Clune, Thomas L, and Yu, Hongfeng

In 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016

Bib
@inproceedings{kuo2016implications, bibtex_show = {true}, abbr = {IGARSS}, title = {Implications of data placement strategy to Big Data technologies based on shared-nothing architecture for geosciences}, author = {Kuo, Kwo-Sen and Oloso, Amidu and Doan, Khoa D and Clune, Thomas L and Yu, Hongfeng}, booktitle = {2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)}, pages = {7605--7607}, year = {2016}, organization = {IEEE} }

2015

AGU SciDB versus Spark: A preliminary comparison based on an Earth science use case

Clune, Thomas, Kuo, Kwo-Sen, Doan, Khoa D, and Oloso, Amidu

In AGU Fall Meeting Abstracts 2015

Bib

@inproceedings{clune2015scidb,
  bibtex_show = {true},
  abbr = {AGU},
  title = {SciDB versus Spark: A preliminary comparison based on an Earth science use case},
  author = {Clune, Thomas and Kuo, Kwo-Sen and Doan, Khoa D and Oloso, Amidu},
  booktitle = {AGU Fall Meeting Abstracts},
  volume = {2015},
  year = {2015}
}

2014

BigData Performance comparison of big-data technologies in locating intersections in satellite ground tracks

Doan, Khoa D, Oloso, Amidu, Kuo, Kwo-Sen, Clune, Thomas L, and Bayesics, LLC

In Proceedings of the 2014 ASE BigData/SocialInformatics/PASSAT/BioMedCom Conference 2014

Bib
@inproceedings{doan2014performance, bibtex_show = {true}, abbr = {BigData}, title = {Performance comparison of big-data technologies in locating intersections in satellite ground tracks}, author = {Doan, Khoa D and Oloso, Amidu and Kuo, Kwo-Sen and Clune, Thomas L and Bayesics, LLC}, booktitle = {Proceedings of the 2014 ASE BigData/SocialInformatics/PASSAT/BioMedCom Conference}, year = {2014}, organization = {Citeseer} }

2013

AGU A Demonstration of Big Data Technology for Data Intensive Earth Science

Kuo, K, Clune, T, Ramachandran, R, Rushing, J, Fekete, G, Lin, A, Doan, KD, Oloso, AO, and Duffy, D

In AGU Fall Meeting Abstracts 2013

Bib
@inproceedings{kuo2013demonstration, bibtex_show = {true}, abbr = {AGU}, title = {A Demonstration of Big Data Technology for Data Intensive Earth Science}, author = {Kuo, K and Clune, T and Ramachandran, R and Rushing, J and Fekete, G and Lin, A and Doan, KD and Oloso, AO and Duffy, D}, booktitle = {AGU Fall Meeting Abstracts}, volume = {2013}, year = {2013} }